agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm
34
0%
Does it follow best practices?
Impact
93%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-tdd-london-swarm/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially non-functional as a skill selector. It provides only an invocation command and an opaque internal name, with zero information about what the skill does, when to use it, or what user requests should trigger it. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.
Suggestions
Add a clear 'what' clause describing concrete actions, e.g., 'Implements London-style (outside-in) test-driven development using mock objects, writing failing tests first then making them pass incrementally.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for TDD, test-driven development, London-style testing, outside-in development, mock-based testing, or writing tests before implementation.'
Include relevant file types, frameworks, or language contexts if applicable (e.g., 'Works with Python/pytest, JavaScript/Jest') to improve distinctiveness and trigger matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only states it's an 'agent skill' and how to invoke it. There is no indication of what the skill actually does beyond the name 'tdd-london-swarm', which is jargon. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command, with no explanation of functionality or trigger conditions. | 1 / 3 |
Trigger Term Quality | No natural keywords a user would say are present. 'tdd-london-swarm' is a technical internal name, not something a user would naturally request. Terms like 'test-driven development', 'London-style TDD', 'outside-in testing', or 'mocking' are entirely absent. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it provides no distinguishing characteristics. The only differentiator is the internal name 'tdd-london-swarm', which doesn't help Claude distinguish this from other agent skills or testing-related skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a verbose conceptual essay about London School TDD and a fictional 'swarm coordination' system rather than actionable guidance. It explains concepts Claude already knows, uses non-existent APIs in its examples, lacks any concrete workflow with validation steps, and presents everything as a monolithic document. The 'swarm' coordination patterns appear entirely invented with no grounding in real tools or frameworks.
Suggestions
Replace fictional swarm APIs (swarmCoordinator, createSwarmMock, SwarmContractMonitor) with real, executable code using actual testing frameworks like Jest, or remove them entirely if they don't correspond to real tools.
Add a concrete step-by-step workflow: e.g., 1. Write failing acceptance test → 2. Run test (verify red) → 3. Create mocks for collaborators → 4. Implement to pass → 5. Verify mock interactions → 6. Run full suite.
Cut the content by at least 60% - remove the 'Core Responsibilities' list, the 'Best Practices' section (Claude knows these), and the conceptual explanations. Keep only the concrete patterns and commands.
Split detailed mock patterns and contract testing examples into separate referenced files, keeping SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~200+ lines. Explains TDD concepts Claude already knows (what outside-in TDD is, what behavior verification means). The 'Core Responsibilities' section is pure description. Many code examples are illustrative/conceptual rather than adding unique knowledge. The 'swarm coordination' patterns use fictional APIs (swarmCoordinator, SwarmContractMonitor) that aren't real tools. | 1 / 3 |
Actionability | The code examples use fictional APIs (swarmCoordinator.notifyTestStart, createSwarmMock, SwarmContractMonitor) that don't exist and aren't executable. The 'swarm coordination' concept is never grounded in real tools or commands. Most examples are pseudocode dressed as TypeScript - they illustrate concepts rather than providing copy-paste-ready guidance. | 1 / 3 |
Workflow Clarity | No clear step-by-step workflow for actually performing TDD. The numbered sections (1, 2, 3) describe concepts rather than sequenced steps. There are no validation checkpoints, no error recovery paths, and no concrete process for when tests fail or mocks need updating. The 'Outside-In Development Flow' doesn't actually describe a flow with steps. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline despite being very long. No navigation structure, no links to detailed references. The content would benefit enormously from splitting mock patterns, swarm coordination, and contract testing into separate referenced files. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/claude-flow
- Commit
f547cec
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.